Agent Plugins Marketplace
← All plugins

reviewops-auditor-benchmark

v0.1.0

Normalize, validate, benchmark, and recommend from declared local review-run evidence offline.

Codex4 Skills

By Tony LoehrLicense: Apache-2.011 GitHub starsUpdated 2 weeks ago

Directory evidence

Runtimes
Codex
Parsed components
4 skill or MCP entries
Source updated
Oct 3, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install reviewops-auditor-benchmark for Codex

Installs for the current user
codex plugin marketplace add openai/community-plugins
codex plugin marketplace upgrade community-plugins
codex plugin add reviewops-auditor-benchmark@community-plugins

Paste and run these commands in a terminal with Codex. They add and refresh the community-plugins catalog, then install this plugin.

Compatibility: the page URL and API slug “reviewops-auditor-benchmark” remain stable.

  • Codex: reviewops-auditor-benchmark@agent-plugin-marketplace → reviewops-auditor-benchmark@community-plugins

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/openai/community-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/reviewops-auditor-benchmark/.

Plugin files

plugins/reviewops-auditor-benchmark/
├── .codex-plugin/plugin.json
├── skills/audit-review-eval-validity/SKILL.md
├── skills/benchmark-review-configs/SKILL.md
├── skills/normalize-review-runs/SKILL.md
└── skills/recommend-review-reference-architecture/SKILL.md

Included Skills4

audit-review-eval-validityskills/audit-review-eval-validity/SKILL.md

Audit whether a declared local review evaluation can support fair quality claims. Use only when the user explicitly asks to audit review-eval validity or use the bundled synthetic fixture.

benchmark-review-configsskills/benchmark-review-configs/SKILL.md

Deterministically score comparable imported review-run lanes with root-cause metrics and uncertainty. Use only when the user explicitly asks to benchmark normalized local review runs or use the bundled synthetic fixture.

normalize-review-runsskills/normalize-review-runs/SKILL.md

Validate and normalize declared local review-run exports into a bounded canonical summary. Use only when the user explicitly asks to normalize review runs or use the bundled synthetic fixture.

recommend-review-reference-architectureskills/recommend-review-reference-architecture/SKILL.md

Recommend a conservative shadow-only review reference architecture from valid offline evidence. Use only when the user explicitly asks for a reference-architecture recommendation or uses the bundled synthetic fixture.

Plugin manifests1

plugins/reviewops-auditor-benchmark/.codex-plugin/plugin.json
{
  "name": "reviewops-auditor-benchmark",
  "version": "0.1.0",
  "description": "Normalize, validate, benchmark, and recommend from declared local review-run evidence offline.",
  "author": {
    "name": "Tony Loehr",
    "url": "https://github.com/tonyloehr"
  },
  "homepage": "https://github.com/tonyloehr/community-plugins/tree/main/plugins/reviewops-auditor-benchmark",
  "repository": "https://github.com/tonyloehr/community-plugins",
  "license": "Apache-2.0",
  "keywords": [
    "code-review",
    "benchmarking",
    "reviewops",
    "quality",
    "developer-tools"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "ReviewOps Auditor + Benchmark",
    "shortDescription": "Evaluate review architectures offline.",
    "longDescription": "Read explicitly declared sanitized local exports, protocols, labels, and pricing snapshots; normalize runs, audit evaluation validity, score fair comparison lanes, and emit shadow-only reference-architecture guidance. Optional static diagnostics remain secondary. This release uses no network, credentials, writeback, or model replay.",
    "developerName": "Tony Loehr",
    "category": "Developer Tools",
    "websiteURL": "https://github.com/tonyloehr/community-plugins",
    "capabilities": [
      "Read"
    ],
    "brandColor": "#2563EB",
    "logo": "./assets/icon.svg",
    "composerIcon": "./assets/icon.svg",
    "defaultPrompt": [
      "Use $normalize-review-runs on the bundled synthetic fixture only. Explain the normalization summary, provenance checks, safety boundaries, and next safe step.",
      "Use $audit-review-eval-validity on the bundled synthetic fixture only. Explain which comparison claim is supported, which controls are held constant, and what would block a recommendation.",
      "Use $benchmark-review-configs on the bundled synthetic fixture only. Explain the eligible root-cause metrics, exclusions, confidence intervals, and risk slice limitations.",
      "Use $recommend-review-reference-architecture on the bundled synthetic fixture only. Explain the claim boundary, preserved production contracts, human approval gate, and no-posting shadow next step."
    ]
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[reviewops-auditor-benchmark on Agent Plugins Marketplace](https://pluginsmp.com/plugins/reviewops-auditor-benchmark)